Leonard Püttmann commited on
Commit
9b8dbaa
·
verified ·
1 Parent(s): cc2dac4

Upload MT5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +32 -32
  2. generation_config.json +6 -6
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,32 +1,32 @@
1
- {
2
- "_name_or_path": "C:\\Users\\leopu\\OneDrive\\Programming\\Python\\llamaestro\\t5\\results\\mt0-opus-it-en-60500",
3
- "architectures": [
4
- "MT5ForConditionalGeneration"
5
- ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 1024,
8
- "d_kv": 64,
9
- "d_model": 512,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
16
- "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "mt5",
20
- "num_decoder_layers": 8,
21
- "num_heads": 6,
22
- "num_layers": 8,
23
- "pad_token_id": 0,
24
- "relative_attention_max_distance": 128,
25
- "relative_attention_num_buckets": 32,
26
- "tie_word_embeddings": false,
27
- "tokenizer_class": "T5Tokenizer",
28
- "torch_dtype": "float32",
29
- "transformers_version": "4.46.3",
30
- "use_cache": true,
31
- "vocab_size": 250112
32
- }
 
1
+ {
2
+ "_name_or_path": "./mt0-Quadrifoglio-mt-it-en-tatoeba/checkpoint-23387",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.47.1",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "decoder_start_token_id": 0,
3
- "eos_token_id": 1,
4
- "pad_token_id": 0,
5
- "transformers_version": "4.46.3"
6
- }
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.47.1"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a022de83d90cfe0ee9bbb13d5cc462210a9a213b5399aa128f031887e05f950
3
  size 1200729512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a11c270eeed77cdf1771b92c8c2ac50b133285f8c3666dcc1cd1dc740d6a95
3
  size 1200729512